Re: [PATCH v3 1/5] vhost-user: Add VIRTIO Shared Memory map request

[Stefan Hajnoczi <stefanha@redhat.com>]

[-- Attachment #1: Type: text/plain, Size: 15369 bytes --]

On Thu, Sep 12, 2024 at 04:53:31PM +0200, Albert Esteve wrote:
> Add SHMEM_MAP/UNMAP requests to vhost-user to
> handle VIRTIO Shared Memory mappings.
> 
> This request allows backends to dynamically map
> fds into a VIRTIO Shared Memory Region indentified
> by its `shmid`. Then, the fd memory is advertised
> to the driver as a base addres + offset, so it
> can be read/written (depending on the mmap flags
> requested) while its valid.
> 
> The backend can munmap the memory range
> in a given VIRTIO Shared Memory Region (again,
> identified by its `shmid`), to free it. Upon
> receiving this message, the front-end must
> mmap the regions with PROT_NONE to reserve
> the virtual memory space.
> 
> The device model needs to create MemoryRegion
> instances for the VIRTIO Shared Memory Regions
> and add them to the `VirtIODevice` instance.
> 
> Signed-off-by: Albert Esteve <aesteve@redhat.com>
> ---
>  hw/virtio/vhost-user.c                    | 122 ++++++++++++++++++++++
>  hw/virtio/virtio.c                        |  13 +++
>  include/hw/virtio/virtio.h                |   5 +
>  subprojects/libvhost-user/libvhost-user.c |  60 +++++++++++
>  subprojects/libvhost-user/libvhost-user.h |  52 +++++++++
>  5 files changed, 252 insertions(+)
> 
> diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
> index 00561daa06..338cc942ec 100644
> --- a/hw/virtio/vhost-user.c
> +++ b/hw/virtio/vhost-user.c
> @@ -115,6 +115,8 @@ typedef enum VhostUserBackendRequest {
>      VHOST_USER_BACKEND_SHARED_OBJECT_ADD = 6,
>      VHOST_USER_BACKEND_SHARED_OBJECT_REMOVE = 7,
>      VHOST_USER_BACKEND_SHARED_OBJECT_LOOKUP = 8,
> +    VHOST_USER_BACKEND_SHMEM_MAP = 9,
> +    VHOST_USER_BACKEND_SHMEM_UNMAP = 10,
>      VHOST_USER_BACKEND_MAX
>  }  VhostUserBackendRequest;
>  
> @@ -192,6 +194,24 @@ typedef struct VhostUserShared {
>      unsigned char uuid[16];
>  } VhostUserShared;
>  
> +/* For the flags field of VhostUserMMap */
> +#define VHOST_USER_FLAG_MAP_R (1u << 0)
> +#define VHOST_USER_FLAG_MAP_W (1u << 1)
> +
> +typedef struct {
> +    /* VIRTIO Shared Memory Region ID */
> +    uint8_t shmid;
> +    uint8_t padding[7];
> +    /* File offset */
> +    uint64_t fd_offset;
> +    /* Offset within the VIRTIO Shared Memory Region */
> +    uint64_t shm_offset;
> +    /* Size of the mapping */
> +    uint64_t len;
> +    /* Flags for the mmap operation, from VHOST_USER_FLAG_* */
> +    uint64_t flags;
> +} VhostUserMMap;
> +
>  typedef struct {
>      VhostUserRequest request;
>  
> @@ -224,6 +244,7 @@ typedef union {
>          VhostUserInflight inflight;
>          VhostUserShared object;
>          VhostUserTransferDeviceState transfer_state;
> +        VhostUserMMap mmap;
>  } VhostUserPayload;
>  
>  typedef struct VhostUserMsg {
> @@ -1749,6 +1770,100 @@ vhost_user_backend_handle_shared_object_lookup(struct vhost_user *u,
>      return 0;
>  }
>  
> +static int
> +vhost_user_backend_handle_shmem_map(struct vhost_dev *dev,
> +                                    VhostUserMMap *vu_mmap,
> +                                    int fd)
> +{
> +    void *addr = 0;
> +    MemoryRegion *mr = NULL;
> +
> +    if (fd < 0) {
> +        error_report("Bad fd for map");
> +        return -EBADF;
> +    }
> +
> +    if (!dev->vdev->shmem_list ||
> +        dev->vdev->n_shmem_regions <= vu_mmap->shmid) {
> +        error_report("Device only has %d VIRTIO Shared Memory Regions. "
> +                     "Requested ID: %d",
> +                     dev->vdev->n_shmem_regions, vu_mmap->shmid);
> +        return -EFAULT;
> +    }
> +
> +    mr = &dev->vdev->shmem_list[vu_mmap->shmid];
> +
> +    if (!mr) {
> +        error_report("VIRTIO Shared Memory Region at "
> +                     "ID %d unitialized", vu_mmap->shmid);
> +        return -EFAULT;
> +    }
> +
> +    if ((vu_mmap->shm_offset + vu_mmap->len) < vu_mmap->len ||
> +        (vu_mmap->shm_offset + vu_mmap->len) > mr->size) {
> +        error_report("Bad offset/len for mmap %" PRIx64 "+%" PRIx64,
> +                     vu_mmap->shm_offset, vu_mmap->len);
> +        return -EFAULT;
> +    }
> +
> +    void *shmem_ptr = memory_region_get_ram_ptr(mr);
> +
> +    addr = mmap(shmem_ptr + vu_mmap->shm_offset, vu_mmap->len,
> +        ((vu_mmap->flags & VHOST_USER_FLAG_MAP_R) ? PROT_READ : 0) |
> +        ((vu_mmap->flags & VHOST_USER_FLAG_MAP_W) ? PROT_WRITE : 0),
> +        MAP_SHARED | MAP_FIXED, fd, vu_mmap->fd_offset);
> +
> +    if (addr == MAP_FAILED) {
> +        error_report("Failed to mmap mem fd");
> +        return -EFAULT;
> +    }
> +
> +    return 0;
> +}
> +
> +static int
> +vhost_user_backend_handle_shmem_unmap(struct vhost_dev *dev,
> +                                      VhostUserMMap *vu_mmap)
> +{
> +    void *addr = 0;
> +    MemoryRegion *mr = NULL;
> +
> +    if (!dev->vdev->shmem_list ||
> +        dev->vdev->n_shmem_regions <= vu_mmap->shmid) {
> +        error_report("Device only has %d VIRTIO Shared Memory Regions. "
> +                     "Requested ID: %d",
> +                     dev->vdev->n_shmem_regions, vu_mmap->shmid);
> +        return -EFAULT;
> +    }
> +
> +    mr = &dev->vdev->shmem_list[vu_mmap->shmid];
> +
> +    if (!mr) {
> +        error_report("VIRTIO Shared Memory Region at "
> +                     "ID %d unitialized", vu_mmap->shmid);
> +        return -EFAULT;
> +    }
> +
> +    if ((vu_mmap->shm_offset + vu_mmap->len) < vu_mmap->len ||
> +        (vu_mmap->shm_offset + vu_mmap->len) > mr->size) {
> +        error_report("Bad offset/len for mmap %" PRIx64 "+%" PRIx64,
> +                     vu_mmap->shm_offset, vu_mmap->len);
> +        return -EFAULT;
> +    }
> +
> +    void *shmem_ptr = memory_region_get_ram_ptr(mr);
> +
> +    addr = mmap(shmem_ptr + vu_mmap->shm_offset, vu_mmap->len,
> +                PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
> +
> +    if (addr == MAP_FAILED) {
> +        error_report("Failed to unmap memory");
> +        return -EFAULT;
> +    }
> +
> +    return 0;
> +}
> +
>  static void close_backend_channel(struct vhost_user *u)
>  {
>      g_source_destroy(u->backend_src);
> @@ -1817,6 +1932,13 @@ static gboolean backend_read(QIOChannel *ioc, GIOCondition condition,
>          ret = vhost_user_backend_handle_shared_object_lookup(dev->opaque, ioc,
>                                                               &hdr, &payload);
>          break;
> +    case VHOST_USER_BACKEND_SHMEM_MAP:
> +        ret = vhost_user_backend_handle_shmem_map(dev, &payload.mmap,
> +                                                  fd ? fd[0] : -1);
> +        break;
> +    case VHOST_USER_BACKEND_SHMEM_UNMAP:
> +        ret = vhost_user_backend_handle_shmem_unmap(dev, &payload.mmap);
> +        break;
>      default:
>          error_report("Received unexpected msg type: %d.", hdr.request);
>          ret = -EINVAL;
> diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
> index 9e10cbc058..ccc4f2cd75 100644
> --- a/hw/virtio/virtio.c
> +++ b/hw/virtio/virtio.c
> @@ -3059,6 +3059,17 @@ int virtio_save(VirtIODevice *vdev, QEMUFile *f)
>      return vmstate_save_state(f, &vmstate_virtio, vdev, NULL);
>  }
>  
> +MemoryRegion *virtio_new_shmem_region(VirtIODevice *vdev)
> +{
> +    MemoryRegion *mr;
> +    ++vdev->n_shmem_regions;
> +    vdev->shmem_list = g_renew(MemoryRegion, vdev->shmem_list,
> +                               vdev->n_shmem_regions);
> +    mr = &vdev->shmem_list[vdev->n_shmem_regions - 1];
> +    mr = g_new0(MemoryRegion, 1);
> +    return mr;
> +}

This function looks broken. shmem_list[] is reallocated so old
MemoryRegion pointers will be dangling pointers. And then the
MemoryRegion is allocated again using g_new0() but there is no way to
retrieve that address again via shmem_list[].

I expected something like this:

  MemoryRegion *virtio_new_shmem_region(VirtIODevice *vdev)
  {
      MemoryRegion *mr;

      assert(vdev->n_shmem_regions < INT_MAX);
      ++vdev->n_shmem_regions;
      vdev->shmem_list = g_renew(MemoryRegion *, vdev->shmem_list,
                                 vdev->n_shmem_regions);
      mr = g_new0(MemoryRegion, 1);
      vdev->shmem_list[vdev->n_shmem_regions - 1] = mr;
      return mr;
  }

> +
>  /* A wrapper for use as a VMState .put function */
>  static int virtio_device_put(QEMUFile *f, void *opaque, size_t size,
>                                const VMStateField *field, JSONWriter *vmdesc)
> @@ -3481,6 +3492,8 @@ void virtio_init(VirtIODevice *vdev, uint16_t device_id, size_t config_size)
>              virtio_vmstate_change, vdev);
>      vdev->device_endian = virtio_default_endian();
>      vdev->use_guest_notifier_mask = true;
> +    vdev->shmem_list = NULL;

shmem_list[] and each MemoryRegion needs to be free somewhere.
virtio_device_instance_finalize()?

> +    vdev->n_shmem_regions = 0;
>  }
>  
>  /*
> diff --git a/include/hw/virtio/virtio.h b/include/hw/virtio/virtio.h
> index 0fcbc5c0c6..d4a2f664d9 100644
> --- a/include/hw/virtio/virtio.h
> +++ b/include/hw/virtio/virtio.h
> @@ -167,6 +167,9 @@ struct VirtIODevice
>       */
>      EventNotifier config_notifier;
>      bool device_iotlb_enabled;
> +    /* Shared memory region for vhost-user mappings. */
> +    MemoryRegion *shmem_list;
> +    int n_shmem_regions;
>  };
>  
>  struct VirtioDeviceClass {
> @@ -286,6 +289,8 @@ void virtio_notify(VirtIODevice *vdev, VirtQueue *vq);
>  
>  int virtio_save(VirtIODevice *vdev, QEMUFile *f);
>  
> +MemoryRegion *virtio_new_shmem_region(VirtIODevice *vdev);
> +
>  extern const VMStateInfo virtio_vmstate_info;
>  
>  #define VMSTATE_VIRTIO_DEVICE \
> diff --git a/subprojects/libvhost-user/libvhost-user.c b/subprojects/libvhost-user/libvhost-user.c
> index 9c630c2170..496268e12b 100644
> --- a/subprojects/libvhost-user/libvhost-user.c
> +++ b/subprojects/libvhost-user/libvhost-user.c
> @@ -1592,6 +1592,66 @@ vu_rm_shared_object(VuDev *dev, unsigned char uuid[UUID_LEN])
>      return vu_send_message(dev, &msg);
>  }
>  
> +bool
> +vu_shmem_map(VuDev *dev, uint8_t shmid, uint64_t fd_offset,
> +             uint64_t shm_offset, uint64_t len, uint64_t flags)
> +{
> +    VhostUserMsg vmsg = {
> +        .request = VHOST_USER_BACKEND_SHMEM_MAP,
> +        .size = sizeof(vmsg.payload.mmap),
> +        .flags = VHOST_USER_VERSION,
> +        .payload.mmap = {
> +            .shmid = shmid,
> +            .fd_offset = fd_offset,
> +            .shm_offset = shm_offset,
> +            .len = len,
> +            .flags = flags,
> +        },
> +    };
> +
> +    if (vu_has_protocol_feature(dev, VHOST_USER_PROTOCOL_F_REPLY_ACK)) {
> +        vmsg.flags |= VHOST_USER_NEED_REPLY_MASK;
> +    }
> +
> +    pthread_mutex_lock(&dev->backend_mutex);
> +    if (!vu_message_write(dev, dev->backend_fd, &vmsg)) {
> +        pthread_mutex_unlock(&dev->backend_mutex);
> +        return false;
> +    }
> +
> +    /* Also unlocks the backend_mutex */
> +    return vu_process_message_reply(dev, &vmsg);
> +}
> +
> +bool
> +vu_shmem_unmap(VuDev *dev, uint8_t shmid, uint64_t shm_offset, uint64_t len)
> +{
> +    VhostUserMsg vmsg = {
> +        .request = VHOST_USER_BACKEND_SHMEM_UNMAP,
> +        .size = sizeof(vmsg.payload.mmap),
> +        .flags = VHOST_USER_VERSION,
> +        .payload.mmap = {
> +            .shmid = shmid,
> +            .fd_offset = 0,
> +            .shm_offset = shm_offset,
> +            .len = len,
> +        },
> +    };
> +
> +    if (vu_has_protocol_feature(dev, VHOST_USER_PROTOCOL_F_REPLY_ACK)) {
> +        vmsg.flags |= VHOST_USER_NEED_REPLY_MASK;
> +    }
> +
> +    pthread_mutex_lock(&dev->backend_mutex);
> +    if (!vu_message_write(dev, dev->backend_fd, &vmsg)) {
> +        pthread_mutex_unlock(&dev->backend_mutex);
> +        return false;
> +    }
> +
> +    /* Also unlocks the backend_mutex */
> +    return vu_process_message_reply(dev, &vmsg);
> +}
> +
>  static bool
>  vu_set_vring_call_exec(VuDev *dev, VhostUserMsg *vmsg)
>  {
> diff --git a/subprojects/libvhost-user/libvhost-user.h b/subprojects/libvhost-user/libvhost-user.h
> index deb40e77b3..ea4902e876 100644
> --- a/subprojects/libvhost-user/libvhost-user.h
> +++ b/subprojects/libvhost-user/libvhost-user.h
> @@ -127,6 +127,8 @@ typedef enum VhostUserBackendRequest {
>      VHOST_USER_BACKEND_SHARED_OBJECT_ADD = 6,
>      VHOST_USER_BACKEND_SHARED_OBJECT_REMOVE = 7,
>      VHOST_USER_BACKEND_SHARED_OBJECT_LOOKUP = 8,
> +    VHOST_USER_BACKEND_SHMEM_MAP = 9,
> +    VHOST_USER_BACKEND_SHMEM_UNMAP = 10,
>      VHOST_USER_BACKEND_MAX
>  }  VhostUserBackendRequest;
>  
> @@ -186,6 +188,24 @@ typedef struct VhostUserShared {
>      unsigned char uuid[UUID_LEN];
>  } VhostUserShared;
>  
> +/* For the flags field of VhostUserMMap */
> +#define VHOST_USER_FLAG_MAP_R (1u << 0)
> +#define VHOST_USER_FLAG_MAP_W (1u << 1)
> +
> +typedef struct {
> +    /* VIRTIO Shared Memory Region ID */
> +    uint8_t shmid;
> +    uint8_t padding[7];
> +    /* File offset */
> +    uint64_t fd_offset;
> +    /* Offset within the VIRTIO Shared Memory Region */
> +    uint64_t shm_offset;
> +    /* Size of the mapping */
> +    uint64_t len;
> +    /* Flags for the mmap operation, from VHOST_USER_FLAG_* */
> +    uint64_t flags;
> +} VhostUserMMap;
> +
>  #if defined(_WIN32) && (defined(__x86_64__) || defined(__i386__))
>  # define VU_PACKED __attribute__((gcc_struct, packed))
>  #else
> @@ -214,6 +234,7 @@ typedef struct VhostUserMsg {
>          VhostUserVringArea area;
>          VhostUserInflight inflight;
>          VhostUserShared object;
> +        VhostUserMMap mmap;
>      } payload;
>  
>      int fds[VHOST_MEMORY_BASELINE_NREGIONS];
> @@ -597,6 +618,37 @@ bool vu_add_shared_object(VuDev *dev, unsigned char uuid[UUID_LEN]);
>   */
>  bool vu_rm_shared_object(VuDev *dev, unsigned char uuid[UUID_LEN]);
>  
> +/**
> + * vu_shmem_map:
> + * @dev: a VuDev context
> + * @shmid: VIRTIO Shared Memory Region ID
> + * @fd_offset: File offset
> + * @shm_offset: Offset within the VIRTIO Shared Memory Region
> + * @len: Size of the mapping
> + * @flags: Flags for the mmap operation
> + *
> + * Advertises a new mapping to be made in a given VIRTIO Shared Memory Region.
> + *
> + * Returns: TRUE on success, FALSE on failure.
> + */
> +bool vu_shmem_map(VuDev *dev, uint8_t shmid, uint64_t fd_offset,
> +                  uint64_t shm_offset, uint64_t len, uint64_t flags);

How is the fd passed to the front-end?

> +
> +/**
> + * vu_shmem_map:

"vu_shmem_unmap:"

> + * @dev: a VuDev context
> + * @shmid: VIRTIO Shared Memory Region ID
> + * @fd_offset: File offset
> + * @len: Size of the mapping
> + *
> + * The front-end un-mmaps a given range in the VIRTIO Shared Memory Region
> + * with the requested `shmid`.
> + *
> + * Returns: TRUE on success, FALSE on failure.
> + */
> +bool vu_shmem_unmap(VuDev *dev, uint8_t shmid, uint64_t shm_offset,
> +                    uint64_t len);
> +
>  /**
>   * vu_queue_set_notification:
>   * @dev: a VuDev context
> -- 
> 2.45.2
> 

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]